Back to skill
Skillv1.0.0
ClawScan security
MIT · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 10:07 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only informational skill about MIT; it requests no credentials, installs nothing, and its instructions are limited to presenting background content — behavior is coherent with its stated purpose.
- Guidance
- This skill is a read-only informational piece about MIT and appears low-risk: it asks for no credentials and installs nothing. Two practical cautions: (1) provenance is unknown (no homepage or source listed), so verify any critical facts against authoritative sources (MIT pages, published research) before relying on them; (2) the SKILL.md is static content in Chinese — if you expect dynamic or up-to-date data (e.g., current research funding, recent faculty), the skill may be out of date and you should prefer authoritative APIs or the official MIT website.
Review Dimensions
- Purpose & Capability
- okThe name/description (an MIT informational skill) matches the SKILL.md content. No binaries, env vars, or config paths are requested, which is proportionate for a read-only informational skill.
- Instruction Scope
- okSKILL.md contains static informational text and a short 'read_when' list indicating topics to present. It does not instruct the agent to access unrelated files, credentials, or external endpoints directly.
- Install Mechanism
- okNo install spec or code files are present (instruction-only), so nothing is written to disk or fetched during installation.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths — this is appropriate for a content-only skill.
- Persistence & Privilege
- okThe skill does not request always:true and uses default invocation settings. It does not ask to modify other skills or system-wide settings.